High‐dimensional Bayesian optimization for metamaterial design by Zhichao Tian, Yang Yang, Sui Zhou, Tian Zhou, Ke Deng, Chunlin Ji, Yejun He, Jun S. Liu

“…First, variational autoencoders (VAEs) are employed for efficient dimensionality reduction, mapping complex, high‐dimensional metamaterial microstructures into a compact latent space. …”
Get full text

Maize Seed Variety Classification Based on Hyperspectral Imaging and a CNN-LSTM Learning Framework by Shuxiang Fan, Quancheng Liu, Didi Ma, Yanqiu Zhu, Liyuan Zhang, Aichen Wang, Qingzhen Zhu

“…This method successfully minimized data dimensionality, reduced variable collinearity, and boosted the model’s stability and computational efficiency. A CNN-LSTM model, built on the selected wavelengths, achieved an accuracy of 95.27% in maize variety classification, outperforming traditional chemometric models like partial least squares discriminant analysis, support vector machines, and extreme learning machines. …”
Get full text

Advancements in Virtual Bioequivalence: A Systematic Review of Computational Methods and Regulatory Perspectives in the Pharmaceutical Industry by Nasser Alotaiq, Doni Dermawan

“…Background/Objectives: The rise of virtual bioequivalence studies has transformed the pharmaceutical landscape, enabling more efficient drug development processes. This systematic review aims to explore advancements in physiologically based pharmacokinetic (PBPK) modeling, its regulatory implications, and its role in achieving virtual bioequivalence, particularly for complex drug formulations. …”
Get full text

Parameter Adaptive LCD Screen Defect Detection Framework by LIU Wang, SHAO Huili, HE Yongjun, XIE Yining, CHEN Deyun

“…It is necessary to detect defects in the production process of LCD screens for quality improvements Manual detection brings a heavy workload and low accuracy Therefore, an efficient and accurate automatic detection method is urgently needed To this end, this paper proposes a new defect detection framework, which mainly includes screen area extraction, preprocessing, threshold segmentation and defect selection By adaptive adjustment of parameters, the detection method can adapt to various complex situations In order to eliminate the influence of illumination changes, the defect region is segmented by automatic parameter adjustment in the threshold segmentation First, the maximum grayscale value of the image is calculated, and then the fixed parameters and the coefficient of the defect image are determined according to the nodefect image, and finally the maximum value which was selected as the minimum threshold of the threshold segmentation from the fixed parameters and the product of the maximum grayscale value and the coefficient In addition, in order to solve the problem that the brightness difference of the images captured by lowresolution cameras is too small to detect defects in the saturation condition, selfadaptive adjustment of exposure parameters was used to collect images to process different parts of images with large difference in light and shade Experiments show that the method can achieve high performance and efficiency in detecting defects such as points, lines, Mura, saturation…”
Get full text

Investigate on the Fluid Dynamics and Heat Transfer Behavior in an Automobile Gearbox Based on the LBM-LES Model by Gaoan Zheng, Pu Xu, Lin Li

“…Under high-temperature conditions (such as 100 °C), the diffusion range of the lubricant increases, forming a wider oil film, but its viscosity significantly decreases, leading to greater stirring losses. By optimizing the selection of lubricants and stirring parameters, the efficiency and reliability of the gear transmission system can be further improved, extending its service life. …”
Get full text

IoT-Based Traffic Prediction for Smart Cities by Zhinong Miao, Qilong Liao

“…The study suggests that integrating advanced machine learning techniques like CNNs and PSO can lead to more efficient and adaptive traffic management solutions, contributing to the development of smarter, more resilient urban environments. …”
Get full text

Kriging-Based Variable Screening Method for Aircraft Optimization Problems with Expensive Functions by Yadong Wang, Xinyao Duan, Jiang Wang, Jin Guo, Minglei Han

“…Therefore, performing variable selection to identify influential inputs becomes crucial for minimizing the number of necessary model evaluations, particularly when dealing with complex systems exhibiting nonlinear and poorly understood input–output relationships. …”
Get full text

Multi-dimensional water quality indicators forecasting from IoT sensors: A tensor decomposition and multi-head self-attention mechanism. by Li Bo, Lv Junrui, Luo Xuegang

“…To overcome these limitations, we propose TGMHA (Tensor Decomposition and Gated Neural Network with Multi-Head Self-Attention), a novel hybrid model that integrates three key innovations: 1) Tensor-based Feature Extraction: We combine Standard Delay Embedding Transformation (SDET) with Tucker tensor decomposition to reconstruct raw time series into low-rank tensor representations, capturing latent spatio-temporal patterns while suppressing sensor noise. 2) Multi-Head Self-Attention for Inter-Indicator Dependencies: A multi-head self-attention mechanism explicitly models complex inter-dependencies among diverse water quality indicators (e.g., pH, dissolved oxygen, conductivity) via parallel feature subspace learning. 3) Efficient Long-Term Dependency Modeling: An encoder-decoder architecture with gated recurrent units (GRUs), optimized by adaptive rank selection, ensures efficient modeling of long-term dependencies without compromising computational performance. …”
Get full text

Construction and Application Analysis of an Intelligent Distribution Network Identification System Based on Deep Neural Networks by Yu Ma

“…OBJECTIVES: This study aims to establish a machine learning-based Intelligent Distribution Network (IDN) online topology recognition model to address the limited measurement equipment in distribution networks and improve the accuracy and efficiency of network topology recognition. METHODS: First, light GBM was used for feature selection to reduce computational complexity and improve learning efficiency. …”
Get full text

Forecasting Tunnel-Induced Ground Settlement: A Hybrid Deep Learning Approach and Traditional Statistical Techniques With Sensor Data by Syed Mujtaba Hussaine, Linlong Mu, Yimin Lu, Syed Sajid Hussain

“…The proposed DL models, Convolutional Long Short-Term Memory (Conv-LSTM2D) and Convolutional Gated Recurrent Unit (Conv-GRU2D), extend traditional LSTM and GRU architectures with 2D convolutional mechanisms to capture complex spatiotemporal dependencies. Additionally, the statistical Autoregressive Integrated Moving Average (ARIMA)/Seasonal ARIMA (SARIMA) models were enhanced through seasonality removal, automated model selection using the auto_arima algorithm, and parameter fine-tuning via grid search to improve their predictive accuracy. …”
Get full text

Research on a Point Cloud Registration Method Based on Dynamic Neighborhood Features by Xinrui Liu, Rutao Wang, Zongsheng Wang

“…This paper introduces a method that can enhance the accuracy and efficiency of point cloud data registration. This method selects the centroid of the point cloud as the feature point and uses the projected distance of this feature point within the dynamic neighborhood to other points as the feature information. …”
Get full text

Research on the A* Algorithm for Automatic Guided Vehicles in Large-Scale Maps by Yuandong Chen, Jinhao Pang, Yuchen Gou, Zhiming Lin, Shaofeng Zheng, Dewang Chen

“…In this study, we aimed to improve the search efficiency and path planning quality of the A* algorithm in complex and large-scale environments through a series of optimisation measures, including the innovation of weight design, flexible adjustment of the search neighbourhood, improvement of the heuristic function, and optimisation of the node selection strategy. …”
Get full text

Conductivity Measurement for Non-Magnetic Materials Using Eddy Current Method with a Novel Simplified Model by Changli Yan, Jun Bao, Xuyang Zheng

“…However, conventional ECT is significantly influenced by the thickness of the material, often resulting in the arbitrary selection of excitation frequency. In addition, complex inverse calculations in the eddy current analytical model pose challenges for practical application. …”
Get full text

Frequency-informed transformer for real-time water pipeline leak detection by Fengnian Liu, Ding Wang, Junya Tang, Lei Wang

“…Existing leak detection methods often face challenges, such as heavily relying on the manual selection of frequency bands or complex feature extraction, which can be both labour-intensive and less effective. …”
Get full text

Methods and effective algorithms for solving multidimensional integral equations by A. B. Samokhin

“…When using a uniform grid, the dimensionality of SLAEs can be several orders of magnitude higher; however, in this case, it may be difficult to describe the complex configuration of the domain. Selection of the particular method depends on the specific problem and available computational resources. …”
Get full text

Hybrid deep learning optimization for smart agriculture: Dipper throated optimization and polar rose search applied to water quality prediction. by Amal H Alharbi, Faris H Rizk, Khaled Sh Gaber, Marwa M Eid, El-Sayed M El-Kenawy, Ehsan Khodadadi, Nima Khodadadi

“…The proposed approach integrates binary feature selection and metaheuristic optimization into a unified optimization process, effectively balancing exploration and exploitation to handle complex, high-dimensional datasets. …”
Get full text

Thermal Engineering Tests of Heating Boiler Houses when Working on Peat Fuel by V. K. Lyubov, D. G. Chukhchin, A. N. Popov

“…The conversion of heat generating plants to peat fuel combustion makes it possible to achieve a significant reduction in emissions of solid and soot particles without upgrading ash-collecting plants. Complex experimental studies conducted of existing hot water boilers with a nominal heating capacity of 0.4 and 2.0 MW have shown the possibility, as well as the energy-environmental efficiency of burning briquetted and sod peat in the combustion chambers of these heat generating plants.…”
Get full text

ATHEMATICAL MODEL FOR THE OPTIMISATION OF HIERARCHICAL MULTI-LEVEL PRODUCTION SYSTEMS by Yu. V. Minaeva

“…It is possible to use the model’s multi-level unification and scalability to increase modelling efficiency and thus optimise complex multinomenclature productions.…”
Get full text

Review on development and utilization of offshore renewable energy: An analysis based on a five-dimensional framework by DU Wenjie, CAI Guotian, Qi Xiaoling, WANG Peng, ZHANG Jixiang

“…However, it also faces challenges such as complex environmental conditions, low reliability, and spatial competition. …”
Get full text

A Study on the Yield Stability of Oilseed Sunflower Genotypes under Drought Stress by Nasrin Akbari, Reza Darvishzadeh

“…Based on this, several methods have been introduced for selection with optimal efficiency and high accuracy. …”
Get full text